Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 429 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Trajectory Prediction | ETH | 47 | May 26, 2026 | ||
| Semantic Segmentation | ADE-847 | 47 | Mar 31, 2026 | ||
| Visual Question Answering | OK-VQA (val) | 47 | Feb 26, 2026 | ||
| Video Question Answering | How2QA | 47 | Feb 26, 2026 | ||
| Precipitation Forecasting | SEVIR (test) | 47 | Jun 16, 2026 | ||
| Backdoor Defense | Tiny-ImageNet (test) | 47 | Feb 26, 2026 | ||
| Semantic Segmentation | ACDC (val) | 47 | Mar 26, 2026 | ||
| Image Inpainting | FFHQ 256x256 (val) | 47 | Jun 30, 2026 | ||
| 3D Object Detection | Waymo Open Dataset (WOD) (val) | 47 | Feb 26, 2026 | ||
| Anomaly Segmentation | Road Anomaly (test) | 47 | Feb 26, 2026 | ||
| Object Detection | BDD100k daytime | 47 | Apr 21, 2026 | ||
| Image Classification | FGSM (test) | 47 | Mar 19, 2026 | ||
| Image Recognition | ImageNet1K 1.0 (val) | 47 | Feb 26, 2026 | ||
| Object Detection | Cityscapes → BDD100k (test) | 47 | Jul 1, 2026 | ||
| Image Classification | VisDA 17 | 47 | Mar 25, 2026 | ||
| Node classification | ogbn-mag (val) | 47 | Feb 26, 2026 | ||
| Spatio-temporal Video Grounding | VidSTG Interrogative Sentences (test) | 47 | Jun 4, 2026 | ||
| Handwritten Mathematical Expression Recognition | CROHME 2014 | 47 | Feb 26, 2026 | ||
| Anomaly Detection | MSL | 47 | May 11, 2026 | ||
| Object Detection | ExDark (test) | 47 | Apr 14, 2026 | ||
| Named Entity Recognition | FewNERD INTRA | 47 | Feb 26, 2026 | ||
| Image Classification | ImageNet ILSVRC2012 (val) | 47 | Feb 26, 2026 | ||
| Gait Recognition | Gait3D (test) | 47 | Apr 30, 2026 | ||
| 3D Human Reconstruction | CAPE | 47 | May 26, 2026 | ||
| 3D Point Cloud Classification | ModelNet40 (test) | 47 | Apr 20, 2026 |